IRIS

An operating system for explanatory models.

by Reckoning Machines


Work the way you think.

IRIS repository index with repository search and investment research workspaces

IRIS is where institutional investment research lives.

Models, Methods, evidence, reports, decisions, and memory remain connected in one repository.

Analyst pain points

Problems IRIS Solves

Context & memory

“What were we thinking going into earnings?”

“I have to paste my numbers into ChatGPT and explain the model every time.”

“Where did this number come from?”

“What changed since last quarter?”

“I need the model we used for the Board meeting.”

Model control

“I’m in a meeting. I don’t have my model.”

“I just saved over the wrong model.”

“Can someone send me the latest model?”

“I have no idea who changed this formula.”

“I want to schedule my model to update every morning before I get in.”

Research at scale

“I changed the model. Now I have to rewrite the note.”

“I want to run every bank model every night and update my dashboard.”

“Our research feels like it doesn’t compound.”

“I wish I could save this prompt with the model.”

Figure 1 The Research Velocity Flywheel The operating model behind IRIS.

Engineering Diagram IRIS Research System
Context to Orientation to Evidence to Continuity to Better Context flywheel

IRIS reduces the time between a question and a decision. Each research cycle preserves the context, evidence, and judgment required for the next one.

Search

Start with the model.

Search is the front door. Open a company, model, question, or research surface without managing files.

IRIS repository search surface for opening models and research surfaces
Search opens the current model and the research surfaces around it.
Analyze

Work in the model.

Keep the familiar grid and familiar formulas, but attach assumptions, outputs, evidence, formulas, and reasoning to the model itself.

The spreadsheet stays familiar. The context becomes durable.

IRIS model screen with spreadsheet and Research Rail panel
Analyze (shown in Blueprint paper) is where model work, assumptions, outputs, and evidence stay in one surface.

METHOD

Teach IRIS how your team works.

=AI("forecast loan growth")

One formula. One Method. Preserved forever.

Methods are reusable analytical procedures.

They preserve not only what your analysts concluded, but how they reached the conclusion.

Every execution strengthens institutional memory.

Research Rail

Ask the model.

Research Rail is the analyst interface to the repository.

  • Why?
  • What changed?
  • What stands out?
  • Have we believed this before?
  • Remember this.
  • What if margin were 5%?
  • Write the report.

Ask questions. Run research. Test scenarios. Build memory.

IRIS Research Rail showing repository context, suggested research actions, and the analyst prompt
Research begins with the model, its current context, and a direct prompt.
Meeting Mode

Take the model into the room.

Meeting Mode turns the repository into a phone-native decision surface. See the current conclusion, key outputs, and model context without opening Excel.

The model stays behind the answer. The answer goes wherever the decision happens.

IRIS Meeting Mode on a phone showing a positive recommendation and key model outputs
Meeting Mode keeps the current conclusion and the numbers behind it in reach.
Report

Turn work into communication.

Reports are emitted from model work. The explanation stays attached to the assumptions, outputs, evidence, and changes that produced it.

IRIS Report editor showing an Apple Investment Thesis with governed data and AI formulas
Compose Write with governed model values and research instructions in the report itself.
Timeline

Preserve what changed.

The timeline keeps institutional memory: what changed, when it changed, and why it mattered. Every decision becomes part of the model's history.

IRIS Timeline showing repository chronology, model lineage, immutable version history, and comparison controls
Timeline records chronology and lineage, from the initial version through the current immutable head.
Serious teams

Serious research teams move faster when the model remembers.

Preserve reasoning. Not files.
Test ideas. Not spreadsheet copies.
Explain changes. Not screenshots.
Build memory. Not archaeology.

One repository.

One timeline.

One Research Rail.

One model.

Everything stays connected.